Investigating Temporal Features of Carotid Intima-Media Thickness from Ultrasound Imaging with Recurrent Neural Networks

Min Jing; Kathryn Owen; Brian Mac Namee; Ian Menown; James McLaughlin

doi:10.1109/EMBC40787.2023.10340661

Investigating Temporal Features of Carotid Intima-Media Thickness from Ultrasound Imaging with Recurrent Neural Networks

Min Jing, Kathryn Owen, Brian Mac Namee, Ian Menown, James McLaughlin

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

31 Downloads (Pure)

Abstract

Measuring carotid intima-media thickness (cIMT) of the Common Carotid Artery (CCA) via B-mode ultrasound imaging is a non-invasive yet effective way to monitor and assess cardiovascular risk. Recent studies using Convolutional Neural Networks (CNNs) to automate the process have mainly focused on the detection of regions of interest (ROI) in single frame images collected at fixed timepoints and have not exploited the temporal information captured in ultrasound imaging. This paper presents a novel framework to investigate the temporal features of cIMT, in which Recurrent Neural Networks (RNN) were deployed for ROI detection using consecutive frames from ultrasound imaging.
The cIMT time series can be formed from estimates of cIMT in each frame of an ultrasound scan, from which additional information (such as min, max, mean, and frequency) on cIMT time series can be extracted. Results from evaluation show the best performance for ROI detection improved 4.75% by RNN compared to CNN-based methods. Furthermore, the heart rate estimated from the cIMT time series for seven patients was highly correlated with the patient’s clinical records, which suggests the potential application of the cIMT time series and related features for clinical studies in the future.

Original language	English
Title of host publication	2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Publisher	IEEE
Pages	1-4
Number of pages	4
Volume	2023
ISBN (Electronic)	979-8-3503-2447-1
ISBN (Print)	979-8-3503-2448-8
DOIs	https://doi.org/10.1109/EMBC40787.2023.10340661
Publication status	Published online - 11 Dec 2023
Event	The 45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) - Sydney, Australia Duration: 24 Jul 2023 → 28 Jul 2023 https://embc.embs.org/2023/

Publication series

Name
ISSN (Print)	2375-7477
ISSN (Electronic)	2694-0604

Conference

Conference	The 45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Country/Territory	Australia
City	Sydney
Period	24/07/23 → 28/07/23
Internet address	https://embc.embs.org/2023/

Bibliographical note

This work was supported by the European Union’s INTERREGVA Programme managed by the Special EU Programmes Body (SEUPB).

Keywords

Heart rate
Time-frequency analysis
Ultrasonic imaging
Recurrent neural networks
Ultrasonic variable measurement
Time series analysis
Imaging

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/EMBC40787.2023.10340661

EMBC2023_MJ_finalAuthor Accepted Manuscript, 777 KB

Cite this

Jing, M., Owen, K., Mac Namee, B., Menown, I., & McLaughlin, J. (2023). Investigating Temporal Features of Carotid Intima-Media Thickness from Ultrasound Imaging with Recurrent Neural Networks. In 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (Vol. 2023, pp. 1-4). IEEE. Advance online publication. https://doi.org/10.1109/EMBC40787.2023.10340661

@inproceedings{f6055dbfadf44c46b712d2a9976799cf,

title = "Investigating Temporal Features of Carotid Intima-Media Thickness from Ultrasound Imaging with Recurrent Neural Networks",

abstract = "Measuring carotid intima-media thickness (cIMT) of the Common Carotid Artery (CCA) via B-mode ultrasound imaging is a non-invasive yet effective way to monitor and assess cardiovascular risk. Recent studies using Convolutional Neural Networks (CNNs) to automate the process have mainly focused on the detection of regions of interest (ROI) in single frame images collected at fixed timepoints and have not exploited the temporal information captured in ultrasound imaging. This paper presents a novel framework to investigate the temporal features of cIMT, in which Recurrent Neural Networks (RNN) were deployed for ROI detection using consecutive frames from ultrasound imaging. The cIMT time series can be formed from estimates of cIMT in each frame of an ultrasound scan, from which additional information (such as min, max, mean, and frequency) on cIMT time series can be extracted. Results from evaluation show the best performance for ROI detection improved 4.75% by RNN compared to CNN-based methods. Furthermore, the heart rate estimated from the cIMT time series for seven patients was highly correlated with the patient{\textquoteright}s clinical records, which suggests the potential application of the cIMT time series and related features for clinical studies in the future.",

keywords = "Heart rate, Time-frequency analysis, Ultrasonic imaging, Recurrent neural networks, Ultrasonic variable measurement, Time series analysis, Imaging",

author = "Min Jing and Kathryn Owen and {Mac Namee}, Brian and Ian Menown and James McLaughlin",

note = "This work was supported by the European Union{\textquoteright}s INTERREGVA Programme managed by the Special EU Programmes Body (SEUPB).; The 45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) ; Conference date: 24-07-2023 Through 28-07-2023",

year = "2023",

month = dec,

day = "11",

doi = "10.1109/EMBC40787.2023.10340661",

language = "English",

isbn = "979-8-3503-2448-8",

volume = "2023",

publisher = "IEEE",

pages = "1--4",

booktitle = "2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)",

address = "United States",

url = "https://embc.embs.org/2023/",

}

Jing, M, Owen, K, Mac Namee, B, Menown, I & McLaughlin, J 2023, Investigating Temporal Features of Carotid Intima-Media Thickness from Ultrasound Imaging with Recurrent Neural Networks. in 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). vol. 2023, IEEE, pp. 1-4, The 45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Sydney, Australia, 24/07/23. https://doi.org/10.1109/EMBC40787.2023.10340661

Investigating Temporal Features of Carotid Intima-Media Thickness from Ultrasound Imaging with Recurrent Neural Networks. / Jing, Min; Owen, Kathryn; Mac Namee, Brian et al.
2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). Vol. 2023 IEEE, 2023. p. 1-4.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Investigating Temporal Features of Carotid Intima-Media Thickness from Ultrasound Imaging with Recurrent Neural Networks

AU - Jing, Min

AU - Owen, Kathryn

AU - Mac Namee, Brian

AU - Menown, Ian

AU - McLaughlin, James

N1 - This work was supported by the European Union’s INTERREGVA Programme managed by the Special EU Programmes Body (SEUPB).

PY - 2023/12/11

Y1 - 2023/12/11

N2 - Measuring carotid intima-media thickness (cIMT) of the Common Carotid Artery (CCA) via B-mode ultrasound imaging is a non-invasive yet effective way to monitor and assess cardiovascular risk. Recent studies using Convolutional Neural Networks (CNNs) to automate the process have mainly focused on the detection of regions of interest (ROI) in single frame images collected at fixed timepoints and have not exploited the temporal information captured in ultrasound imaging. This paper presents a novel framework to investigate the temporal features of cIMT, in which Recurrent Neural Networks (RNN) were deployed for ROI detection using consecutive frames from ultrasound imaging. The cIMT time series can be formed from estimates of cIMT in each frame of an ultrasound scan, from which additional information (such as min, max, mean, and frequency) on cIMT time series can be extracted. Results from evaluation show the best performance for ROI detection improved 4.75% by RNN compared to CNN-based methods. Furthermore, the heart rate estimated from the cIMT time series for seven patients was highly correlated with the patient’s clinical records, which suggests the potential application of the cIMT time series and related features for clinical studies in the future.

AB - Measuring carotid intima-media thickness (cIMT) of the Common Carotid Artery (CCA) via B-mode ultrasound imaging is a non-invasive yet effective way to monitor and assess cardiovascular risk. Recent studies using Convolutional Neural Networks (CNNs) to automate the process have mainly focused on the detection of regions of interest (ROI) in single frame images collected at fixed timepoints and have not exploited the temporal information captured in ultrasound imaging. This paper presents a novel framework to investigate the temporal features of cIMT, in which Recurrent Neural Networks (RNN) were deployed for ROI detection using consecutive frames from ultrasound imaging. The cIMT time series can be formed from estimates of cIMT in each frame of an ultrasound scan, from which additional information (such as min, max, mean, and frequency) on cIMT time series can be extracted. Results from evaluation show the best performance for ROI detection improved 4.75% by RNN compared to CNN-based methods. Furthermore, the heart rate estimated from the cIMT time series for seven patients was highly correlated with the patient’s clinical records, which suggests the potential application of the cIMT time series and related features for clinical studies in the future.

KW - Heart rate

KW - Time-frequency analysis

KW - Ultrasonic imaging

KW - Recurrent neural networks

KW - Ultrasonic variable measurement

KW - Time series analysis

KW - Imaging

UR - https://embc.embs.org/2023/

UR - http://www.scopus.com/inward/record.url?scp=85179637824&partnerID=8YFLogxK

U2 - 10.1109/EMBC40787.2023.10340661

DO - 10.1109/EMBC40787.2023.10340661

M3 - Conference contribution

C2 - 38083237

SN - 979-8-3503-2448-8

VL - 2023

SP - 1

EP - 4

BT - 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)

PB - IEEE

T2 - The 45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

Y2 - 24 July 2023 through 28 July 2023

ER -

Investigating Temporal Features of Carotid Intima-Media Thickness from Ultrasound Imaging with Recurrent Neural Networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this